6.1.0.0

Identical to version 6.1 on CRAN.

6.0.5.0

It is now possible to specify more than one lag in the ivp function, which is evaluated only when the mif2 perturbations are specified. See ?mif2.

6.0.4.0

• The new function append_data appends a data frame to an existing CSV file (creating the file if it does not exist). This facilitates keeping a database of parameter-space explorations.
• The new function eeulermultinom gives the expectation of an Euler-multinomial random variable.

6.0.2.2

The save.states option to ‘pfilter’ has changed. See ?pfilter and ‘?saved_states for details.

6.0.1.0

This release contains two breaking changes.

• From version 5.8.4, the manner in which extra model elements (userdata) are supplied has changed. As of that version, use of the old method generated a warning. As of this version, an error will be generated. To supply additional elements (i.e., beyond parameters, latent-state variables, observations, and covariates) to the basic model components, provide them as a list via the userdata argument.
• In calls to pomp elementary and inference algorithms, it is now necessary to pass all arguments by name. This has always been good practice, but from this release, calls that rely on the position of arguments will typically generate errors.

See the news blog for more detail.

5.11.1.0

• A new addition to the C API allows one to easily compute the expectation of the Euler-multinomial.
  The function is eeulermultinom.
• The help-page discussion of accumulator variables has been expanded and clarified.

5.11.0.0

Identical to CRAN version 5.11.

5.10.0.3

An improper typecast in the C snippet system, which was resolvable by many compilers but threw an error under recent versions of clang on MacOS, has been repaired.

5.10.0.0

This is identical to version 5.10 on CRAN.

5.9.1.0

The rprocess plugin onestep now always takes exactly one step to get from one observation time to the next, even when the interval between them is zero. That is, if P is a 'pomp' object with an rprocess built using rprocess=onestep(f), t0=timezero(P), and t=time(P), then f will be called exactly once for the interval (t0,t[1]) and once for each of the intervals (t[i-1],t[i]), i=2,...,length(t).